Get more information from the user when the initial prompt isn't sufficiently clear

Alert users to actions they can take to use AI, especially if they are just getting started

Solves the blank canvas dilemma with clues for how to prompt

Structured templates that can be filled by the user or pre-filled by the AI

Makes it easy for users to extend a prompt to multiple inputs at once

Ask or interact with AI contextually based on something already available on the page

Repeatedly run generative tasks without compromising on the format or accuracy

Open ended prompt inputs that can be used in AI conversations and other natural language prompting

Combine prompts with each other or other sources to get new results

Have AI distill a topic or resource down to its essence

Distill or reorganize complicated information into simple structure

Construct a prompt with raw tokens, just like building with legos

Constrain the inputs or the outputs of the AI by source, type, modality, etc

Target specific areas of the AI's result to regenerate or remix

Let users specify what model to use for their prompts

Include constraints with your prompt for the AI to reference when generating its result

Ensure outputs match your voice, tone, and preferences in a consistent way

Give the AI a specific reference to anchor its response

See and manage what additional sources the AI references to generate its response

String generative steps together to synthesize, create, or send content on auto-pilot

Lets the AI give inline annotations to cite its sources

Manage the flow of information or pause a request mid-stream to adjust the prompt

Let users trace the AI's steps from prompt to result

Show users what is actually happening behind the scenes

Have the AI reproduce its response to the prompt without additional input

Confirm the user's intent for complicated prompts

Have the AI show the steps it will take to respond to the user's prompt before it executes its response

Reveal the tokens the AI used to craft its response

Trace through multiple variations of a result to choose the one that works best for them

Interact with the AI without leaving any traces

Control what details the AI knows about you

Identifiers on AI Generative content that humans, software, or programs can read

Control how the model remembers and uses your data

Signal expectation gaps or errors in the model – but is that clear to the user?

Inform users about shortcomings or risks in the model or the technology overall

Visual cues to help users identify AI features or content

Clearly mark content and interactions guided or delivered by AI

Large, open-ended input inviting the user to start their first interaction with the AI

How do we refer to the AI?

Characteristics that distinguish the AI's personality and vibe

Images that represent the AI within the interface